From 2f28761c9e714b655155ff126013638b9ee328f0 Mon Sep 17 00:00:00 2001 From: trondtynnol Date: Fri, 20 Dec 2024 20:06:24 +0100 Subject: [PATCH] Adding some LC_ALL=C's to make sorting in lemma testing behave as intended --- .../test/generate-adjective-lemmas.sh.in | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/src/fst/morphology/test/generate-adjective-lemmas.sh.in b/src/fst/morphology/test/generate-adjective-lemmas.sh.in index 68b86392..af2fd0be 100755 --- a/src/fst/morphology/test/generate-adjective-lemmas.sh.in +++ b/src/fst/morphology/test/generate-adjective-lemmas.sh.in @@ -99,23 +99,23 @@ for f in $fsttype; do # store it: # Generer lemmaer i adjectives med +A+Sg+Nom, lagre i generated-adjectives sed 's/$/+A+Sg+Nom/' $lemmas | $lookup_tool $generator_file.$suffix | \ - cut -f2 | grep -v "A+" | grep -v "^$" | sort -u > $generated_lemmas.$f.txt + cut -f2 | grep -v "A+" | grep -v "^$" | LC_ALL=C sort -u > $generated_lemmas.$f.txt # Generer lemmaer i adjectives med +A+Superl+Sg+Nom, lagre i generated-adjectives sed 's/$/+A+Der\/Superl+A+Sg+Nom/' $lemmas | $lookup_tool $generator_file.$suffix | \ - cut -f2 | grep -v "A+" | grep -v "^$" | sort -u >> $generated_lemmas.$f.txt + cut -f2 | grep -v "A+" | grep -v "^$" | LC_ALL=C sort -u >> $generated_lemmas.$f.txt # Generer lemmaer i adjectives med +A+Comp+Sg+Nom, lagre i generated-adjectives sed 's/$/+A+Der\/Comp+A+Sg+Nom/' $lemmas | $lookup_tool $generator_file.$suffix | \ - cut -f2 | grep -v "A+" | grep -v "^$" | sort -u >> $generated_lemmas.$f.txt + cut -f2 | grep -v "A+" | grep -v "^$" | LC_ALL=C sort -u >> $generated_lemmas.$f.txt # Generer lemmaer i adjectives med +A+Attr, lagre i generated-adjectives sed 's/$/+A+Attr/' $lemmas | $lookup_tool $generator_file.$suffix | \ - cut -f2 | grep -v "A+" | grep -v "^$" | sort -u >> $generated_lemmas.$f.txt + cut -f2 | grep -v "A+" | grep -v "^$" | LC_ALL=C sort -u >> $generated_lemmas.$f.txt # Generer lemmaer i adjectives med +A+ABBR, lagre i generated-adjectives sed 's/$/+A+ABBR/' $lemmas | $lookup_tool $generator_file.$suffix | \ - cut -f2 | grep -v "A+" | grep -v "^$" | sort -u >> $generated_lemmas.$f.txt + cut -f2 | grep -v "A+" | grep -v "^$" | LC_ALL=C sort -u >> $generated_lemmas.$f.txt # Generer plurale lemmaer i filtered-adjectives med +N+Pl+Nom (som ikke lar seg generere med +A+Sg+Nom). # Lagre dem i generated-adjectives @@ -130,11 +130,11 @@ for f in $fsttype; do # stored and opened in SEE: # Sorter, unifiser - sort -u -o $lemmas $lemmas - sort -u -o $generated_lemmas.$f.txt $generated_lemmas.$f.txt + LC_ALL=C sort -u -o $lemmas $lemmas + LC_ALL=C sort -u -o $generated_lemmas.$f.txt $generated_lemmas.$f.txt # Open the diff file in SubEthaEdit (if there is a diff): - LC_ALL=no_NO.UTF-8 comm -23 $lemmas $generated_lemmas.$f.txt > $result_file.$f.txt + LC_ALL=C comm -23 $lemmas $generated_lemmas.$f.txt > $result_file.$f.txt if [ -s $result_file.$f.txt ]; then grep -v '^$' $result_file.$f.txt \